Sohyun An

PhD student at UCLA

UCLA CS

Biography

I’m a Ph.D. student in the Computational Machine Learning Group at UCLA, under the supervision of Prof. Cho-Jui Hsieh. Previously, I was an M.S. student in the Machine Learning and Artificial Intelligence (MLAI) Lab at KAIST AI, supervised by Prof. Sung Ju Hwang.

I am interested in developing machine learning algorithms to foster the AI-based application ecosystem. I believe this goal can be achieved by efficiently & effectively solving tasks using various search and optimization techniques within a defined search space, while also ensuring that these algorithms are applicable to real-world scenarios.

Recent News

May 2024 : 🎉 One paper accepted to ICML 2024.
Mar 2024 : ✈️ Travel Grant for ICLR 2024 from ICLR Organizers.
Jan 2024 : 🎉 One paper accepted to ICLR 2024.
Jul 2023 : ✈️ Travel Grant for AutoML 2023 from AutoML Organizers.
Apr 2023 : ✈️ Google Travel Grant for ICLR 2023 from Google.
Jan 2023 : 🎉 One paper accepted to ICLR 2023 as Notable-top-25% - Spotlight Presentation.

Interests

Generative Models / LLMs
Search / Optimization
AutoML / Meta-learning

Education

PhD in Computer Science, Sep 2024 - Present
University of California, Los Angeles (UCLA)
MS in Artificial Intelligence, Aug 2022 - Aug 2024
Korea Advanced Institute of Science and Technology (KAIST)
BS in Material Science and Engineering (Summa Cum Laude), Mar 2017 - Aug 2021
Seoul National University (SNU)

Publications

Quickly discover relevant content by filtering publications.

Sohyun An (2024). Optimal Neural Architecture Generation with Diffusion Models. KAIST M.S. Thesis 2024.

Cite PDF

Ruochen Wang*, Sohyun An*, Minhao Cheng, Tianyi Zhou, Sung Ju Hwang, Cho-Jui Hsieh (2024). One Prompt is not Enough: Automated Construction of a Mixture-of-Expert Prompts. ICML 2024.

Cite PDF

Sohyun An*, Hayeon Lee*, Jaehyeong Jo, Seanie Lee, Sung Ju Hwang (2024). DiffusionNAG: Predictor-guided Neural Architecture Generation with Diffusion Models. ICLR 2024.

Cite PDF Code

Hayeon Lee*, Sohyun An*, Minseon Kim, Sung Ju Hwang (2023). Meta-prediction Model for Distillation-Aware NAS on Unseen Datasets. ICLR 2023, Spotlight (notable-top-25%).

Cite PDF Code

Hayeon Lee*, Sohyun An*, Minseon Kim, Sung Ju Hwang (2022). Lightweight Neural Architecture Search with Parameter Remapping and Knowledge Distillation. AutoML 2022 Workshop.

Cite PDF